A neural network-based control chart for monitoring and interpreting autocorrelated multivariate processes using layer-wise relevance propagation

Abstract

Recent advances in sensing and information technology are enabling multivariate sensory data from industrial equipment to be collected at a high sampling frequency. The resulting data streams often exhibit strong autocorrelation. In this study, we propose a neural network-based residual control chart to monitor the autocorrelated multivariate processes for real-time detection of abnormal equipment performance. Furthermore, we propose an interpretation method, based on layer-wise relevance propagation (LRP), to identify the responsible variable when an out-of-control condition is detected by the control chart. We compare the proposed techniques with several existing methods. Numerical studies and a real-data application demonstrate that the proposed method has good monitoring performance and can provide effective interpretation results. The proposed methods can be applied broadly for system condition monitoring and change detection in a variety of industrial systems applications.

Keywords:

• interpretation
• layer-wise relevance propagation
• multivariate control chart
• neural network

About the Authors

Jinwen Sun received the B.S. degree in quality and reliability engineering and M.S. in control science and engineering from Beihang University, in 2016 and 2019, respectively. He is currently working toward the Ph.D. degree at the Department of Industrial and Systems Engineering, University of Wisconsin–Madison, Madison, WI, USA. His research interests include data-driven monitoring, diagnosis and prognosis for manufacturing systems.

Shiyu Zhou received the B.S. and M.S. degrees in mechanical engineering from the University of Science and Technology of China, Hefei, China, in 1993 and 1996, respectively, and the master's degree in industrial engineering and the Ph.D. degree in mechanical engineering from the University of Michigan, Ann Arbor, MI, USA, both in 2000. He is the Vilas Distinguished Achievement Professor with the Department of Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA. His research interests include data-driven modeling, monitoring, diagnosis, and prognosis for engineering systems with particular emphasis on manufacturing and after-sales service systems. Dr. Zhou is a recipient of a CAREER Award from the National Science Foundation and the Best Application Paper Award from IIE Transactions. He is currently the Director of the IoT Systems Research Center at the University of Wisconsin-Madison and a Fellow of the IISE, the ASME, and the SME. [email protected]

Dharmaraj Veeramani received the B.S. degree in mechanical engineering from the Indian Institute of Technology Madras, Chennai, India, in 1985, and the M.S. and Ph.D. degrees in industrial engineering from Purdue University, West Lafayette, IN, USA, in 1987 and 1991, respectively. He is the E-Business Chair Professor with the Department of Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA. He has received numerous research grants from federal agencies and industry. His research focuses on emerging frontiers of digital business, Internet of Things technologies and applications, smart and connected systems, and supply chain management. Dr. Veeramani has received multiple honors and awards from organizations, such as the National Science Foundation, the SME, the SAE International, and the ASEE in recognition of his scholarly contributions.

Acknowledgements

The authors wish to thank Danielle Chrun, Lance D Staudacher and the analytics team of National Oilwell Varco for providing the data and associated guidance for this research. The authors also thank the editor and the referees for their helpful review and constructive comments, which improved the quality of the article greatly.